An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Ada to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Monitor conversations and manage knowledge bases directly from your agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through Ada.

  1. 01

    Create article

    The create_article capability lets you add a brand new text article to the Ada knowledge base, requiring a title and text content to immediately improve bot responses.

  2. 02

    List conversations

    Use list_conversations to pull details on both active and past customer support conversations handled by the Ada bot.

  3. 03

    Get end user

    Use this capability to retrieve profile information and custom metavariables for a specific Ada end user, requiring only the End User ID.

  4. 04

    List articles

    Run list_articles to retrieve the full catalog of help articles that your Ada AI agent uses when answering customer questions.

Real work

What teams actually run

01

Auditing Support Quality

A support manager needs to check if the bot is handling billing questions correctly. They use the MCP to list past conversations and audit the transcripts for gaps.

02

Updating Company Policy

The legal team changes a privacy policy. Instead of waiting for a manual update, they use the MCP to create a new knowledge article instantly.

03

Onboarding New Users

A new user signs up. The support team uses the MCP to pull their profile and sync their metadata into the CRM for continuity.

04

Reviewing Resolution Rates

The operations lead wants to know if the bot is getting better. They use the MCP to retrieve insights on automated resolution rates.

Automate a task

Put Ada to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Ada works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Ada to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

910ms average. Fast in production.

Ada is checked daily against the live service.

Daily averagePeak 1073ms
Oct 3Today
Fastest day
694ms
Slowest day
1073ms
14-day trend
Slowing+9%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Ada, so you can see the experience inside your AI.

It does not authenticate your account with Ada. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Ada Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_AzLRmp3uK52IN3iowI4nfLlOj7D2qBhC9fZYSMTS/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Ada capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ada-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_AzLRmp3uK52IN3iowI4nfLlOj7D2qBhC9fZYSMTS/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Ada in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Ada owners hand off.

This MCP is built for teams that manage high-volume customer interactions. If your goal is to improve bot accuracy, audit support quality, or keep user data consistent across platforms, this connector gives your agent the capabilities you need. It works for operations teams, support managers, and developers building custom AI workflows.

  • 01

    Customer Experience Managers

    Monitor automated conversation quality and find gaps in your current automation.

  • 02

    Support Operations Teams

    Sync user data and manage knowledge base articles efficiently across systems.

  • 03

    Developers

    Integrate Ada's conversational AI into custom applications and complex workflows.

  • 04

    AI Training Leads

    Audit bot responses and update knowledge sources instantly to improve performance.

FAQ

Questions Ada owners ask.

  • 01

    What kind of data can I retrieve about customer conversations?

    You can list and retrieve details for both active and past support conversations. This helps you identify common trends and measure bot performance.

  • 02

    Does this MCP help me improve the bot’s answers?

    Yes. You can use the MCP to create and update articles in the knowledge base. This ensures your AI agent always has the most current information to provide accurate answers.

  • 03

    Is user data synced between Ada and my other systems?

    The MCP allows you to manage user profiles and sync metadata, keeping user data consistent across your external systems.

  • 04

    What if I need to check a specific user's details?

    You can use the get_end_user capability. You just need the End User ID, and the MCP will pull the profile and custom metadata for you.

  • 05

    Can I update my knowledge base via the agent?

    Yes! Use the create_article capability to add new information to your Ada knowledge base. This helps the AI bot stay up-to-date with your latest product or policy changes.

  • 06

    What are the API rate limits on Ada?

    The default platform API limit is 10,000 requests per day (10 per second). Some specific endpoints, such as the Data Export API, have additional limits like 15,000 requests per day.

  • 07

    Are there quotas per knowledge article in Ada?

    Yes, Knowledge Base APIs enforce a constraint of 100KB per individual article, up to a maximum limit of 50,000 global articles in your organization.

Explore

More in Customer Support

Suggestions

Connect Ada to Claude, Cursor, ChatGPT & more